AI-driven early warning systems for IoT cyber threats
Abhiraj Bhaskar Ubaleabu.comp@coeptech.ac.inDepartment of Computer Science and EngineeringCOEP Technological UniversityPune, Maharashtra, 411005, IndiaView full profile → , Vijay Kotkarvijay.kotkar@pccoer.inDepartment of Computer EngineeringPimpri Chinchwad Education Trust’sPimpri Chinchwad College of Engineering and ResearchRavet, Pune, Maharashtra, 412101, IndiaView full profile → , *Sayali D. JoshiCorresponding authorsayalidjoshi@gmail.comDepartment of Information TechnologyMararhwada Mitra Mandal’s College of EngineeringPune, Maharashtra, 411052, IndiaView full profile → , Milind S. Patilmilind.patil@vit.eduDepartment of Electronics & Telecommunication EngineeringVishwakarma Institute of TechnologyPune, Maharashtra, 411037, IndiaView full profile → , Puneet Kumar Yadavpuneet.yadav1@niu.edu.inDepartment of Computer Science & EngineeringNoida International UniversityGreater Noida, Uttar Pradesh, 203201, IndiaView full profile → , V. S. N. Kumarvsnkumar@gmail.comDepartment of Computer ScienceAditya Degree & PG Colleges (Autonomous)Kakinada, Andhra Pradesh, 533003, IndiaView full profile →
* Corresponding author · click or hover a name for details
- Received:
- 01 Apr 2026
- Published Online:
- 31 Oct 2026
- Article type:
- Research Article
- Language:
- EN
- Article no.:
- JDMSC-3022
- Pages:
- 3951–3961
Abstract
Internet of Things (IoT) ecosystems has been associated with serious cybersecurity threats due to the heterogeneous nature, dynamism in connectivity, and poor computing abilities. The present paper presents an AI-based early warning system, which is strong in detecting and predicting cyber threats in an IoT environment, with a high accuracy and low latency. The framework is a combination of sequential learning algorithms, i.e., BiLSTM and GRU, to learn temporal anomalies of network traffic, and Graph Neural Networks (GNN) to learn complex interactions among devices. A hybrid ensemble of Autoencoder based anomaly detectors and XGBoost based classification can achieve an improved predictive performance and a reduced false positives. It has a distributed monitoring and edge intelligence layer to mitigate threats in real time by processing real time data. The experimental results indicate that the proposed system is more accurate in detecting and has a shorter response time and higher system robustness and hence can be applied to scalable and security-critical internet of things applications in other domains.
Keywords
Subject Classifications
References
[1] W. Zhao and P. Wang, “AI-Driven Cybersecurity in IoT-Based Systems,” Sensors, vol. 25, no. 23, Art. no. 7254 (2025), doi: 10.3390/s25237254.
[2] I. Mutambik, “AI-Driven Cybersecurity in IoT: Adaptive Malware Detection and Lightweight Encryption via TRIM-SEC Framework,” Sensors, vol. 25, no. 22, Art. no. 7072 (2025), doi: 10.3390/s25227072.
[3] M. J. C. S. Reis, “AI-Driven Anomaly Detection for Securing IoT Devices in 5G-Enabled Smart Cities,” Electronics, vol. 14, no. 12, Art. no. 2492 (2025), doi: 10.3390/electronics14122492.
[4] M. H. Alsulami, “An AI-Driven Model to Enhance Sustainability for the Detection of Cyber Threats in IoT Environments,” Sensors, vol. 24, no. 22, Art. no. 7179 (2024), doi: 10.3390/s24227179.
[5] M. A. Siam, K. Y. Lucky, S. N. Hasan, J. Kaur, H. Kaur, M. S. Uddin, and M. M. T. G. Manik, “Cybersecure Intelligent Sensor Framework for Smart Buildings: AI-Based Intrusion Detection and Resilience Against IoT Attacks,” Sensors, vol. 25, no. 24, Art. no. 7680 (2025), doi: 10.3390/s25247680.
[6] R. Abreu, E. Simão, C. Serôdio, F. Branco, and A. Valente, “Enhancing IoT Security in Vehicles: A Comprehensive Review of AI-Driven Solutions for Cyber-Threat Detection,” AI, vol. 5, no. 4, pp. 2279–2299 (2024), doi: 10.3390/ai5040112.
[7] E. Skoubris and G. Hloupis, “An AI-Powered, Low-Cost IoT Node Oriented to Flood Early Warning Systems,” Engineering Proceedings, vol. 58, no. 1, Art. no. 44 (2023), doi: 10.3390/ecsa-10-16023.
[8] Warin Sripanya, Wannarut Rungrottheera, and Pacharapol Hyunsin, “Fourier series analysis and computation based on function characteristics,” Journal of Interdisciplinary Mathematics, vol. 28, no. 6, pp. 2109–2120 (2025), doi: 10.47974/JIM-2352.
[9] A. Oacheșu, K. S. Adewole, A. Jacobsson, and P. Davidsson, “Enhancing IoT Security with Generative AI: Threat Detection and Countermeasure Design,” Electronics, vol. 15, no. 1, Art. no. 92 (2026), doi: 10.3390/electronics15010092.
[10] M. Esposito, L. Palma, A. Belli, L. Sabbatini, and P. Pierleoni, “Recent Advances in Internet of Things Solutions for Early Warning Systems: A Review,” Sensors, vol. 22, no. 6, Art. no. 2124 (2022), doi: 10.3390/s22062124.
[11] S. Fernandes-Pereira, “Deep Learning and Optimization Approaches in Deep Convolutional U-Shape Network with Jump Attention-Based Vision Transformer for Integrated Sequence Scheduling and Trajectory Planning with Obstacle Avoidance in Wireless Rechargeable Sensor Networks: A Rev,” IJEECS, vol. 14, no. 1, pp. 353–359 (Apr. 2025).
[12] M. Chaturvedi, S. Sharma, G. Ahmed, and V. Bhatnagar, “Implementation of localized frequency transform-based encryption for enhanced cybersecurity in communication networks,” Journal of Discrete Mathematical Sciences and Cryptography, vol. 29, no. 1, pp. 169–178 (2026), doi: 10.47974/JDMSC-2533.
[13] S. Quaye, A. H. Khan, K. Tapre, and M. Dawson, “AI-Powered Cybersecurity Models for Training and Testing IoT Devices,” Applied Sciences, vol. 15, no. 24, Art. no. 13073 (2025), doi: 10.3390/app152413073.
[14] R. C. Poonia, R. Almakki, A. K. J. Saudagar, A. Altameem, and M. Albathan, “An optimization approach for real-time object detection in IoT devices through edge computing and deep learning,” Journal of Information and Optimization Sciences, vol. 45, no. 5, pp. 1465–1475 (2024), doi: 10.47974/JIOS-1768.
